Skip to content
By using AWS re:Post, you agree to the AWS re:Post Terms of Use
AWS re:Postre:Post
About re:Post

Glue: Change point detection

0

In time series data in AWS Glue I would like to detect the times when statistically significant and sustained changes happen to the data. I then would like to break this time series up into segments. This is known as "change point detection". Is there already something built-into Glue that I can use from the shelf? Or do I have to use libraries like "ruptures" ? Or implement on my on with sliding windows in PySpark?

Topics
Analytics
Tags
AWS Glue
Language
English
asked 3 years ago308 views
1 Answer
1

Glue doesn't provide at this time special features for time series.
To use rupture you probably would need to do it on some aggregated points (lower granularity) if you want to be able to scale to high volume distributed data.
The other option as you say is building your own logic using moving windows in PySpark.

AWS
EXPERT
answered 3 years ago

You are not logged in. Log in to post an answer.

A good answer clearly answers the question and provides constructive feedback and encourages professional growth in the question asker.

Relevant content